All models

Ministral 3 Reasoning

by Mistral AI

Chat Tools Thinking

Mistral AI's Ministral 3 Reasoning (mistral3 family) — tool use, reasoning; 262K context.

Publisher
Mistral AI
Context window
256K tokens
Sizes
3B, 8B, 14B
Licence
Apache 2.0
Model card on Hugging Face

Run Ministral 3 Reasoning

Install it on a Pendra worker, then call it through the OpenAI-compatible API with a pdr_sk_ key.

from pendra import Pendra

client = Pendra(api_key="pdr_sk_...")

response = client.chat.completions.create(
    model="ministral-3-reasoning:3b",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

Run Ministral 3 Reasoning on your own UK infrastructure

Deploy a worker, install Ministral 3 Reasoning, and start serving it through one sovereign API endpoint.